YOLOD: A Target Detection Method for UAV Aerial Imagery

Luo, Xudong; Wu, Yiquan; Zhao, Langyue

doi:10.3390/rs14143240

Cited by 33 publications

(14 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, various machine and deep learning methods have been used to increase the probability of target recognition. Research on probabilistic searches includes [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 ], and search methods using artificial intelligence include [ 28 , 29 , 30 , 31 , 32 ]. Symington et al [ 20 ] conducted an early study on stochastic searches.…”

Section: Related Workmentioning

confidence: 99%

“…The YOLO model introduced by Redmon et al in 2015 [ 33 ] detects objects immediately after looking at the image only once. Tan et al [ 28 ] and Luo et al [ 29 ] proposed an improved algorithm using the existing YOLO v4 algorithm to improve the target detection performance from images captured by UAVs. Luo et al [ 30 ] proposed an improved YOLO v5 algorithm using the k-means++ algorithm.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Improved A-Star Search Algorithm for Probabilistic Air Pollution Detection Using UAVs

2024

Sensors

View full text Add to dashboard Cite

Recently, air pollution problems in urban areas have become serious, and unmanned aerial vehicles (UAVs) can be used to monitor air pollution because they can perform spatial movement. However, because air pollution sources are fluid, probabilistic search methods are required to identify a target through the probability of its existence. This study proposes an efficient algorithm to detect air pollution in urban areas using UAVs. An improved A-star algorithm that can efficiently perform searches based on a probabilistic search model using a UAV is designed. In particular, in the proposed improved A-star algorithm, several special weights are used to calculate the probability of target existence. For example, a heuristic weight based on the expected target, a weight based on data collected from the drone sensor, and a weight based on the prior information of obstacles presence are determined. The method and procedure for applying the proposed algorithm to the stochastic search environment of a drone are described. Finally, the superiority of the proposed improved A-star algorithm is demonstrated by comparing it with existing stochastic search algorithms through various practical simulations. The proposed method exhibited more than 45% better performance in terms of successful search rounds compared with existing methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Improved A-Star Search Algorithm for Probabilistic Air Pollution Detection Using UAVs

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…In a recent study, a new attention module named the IECA [48] has was proposed. It not only alleviates the inefficiency of the Squeeze-and-Excitation (SE) module [49] caused by acquiring all channel dependencies but also makes full use of the gains brought by different pooling methods.…”

Section: Add the Channel Attention Modulementioning

confidence: 99%

Target Detection Method of UAV Aerial Imagery Based on Improved YOLOv5

Luo

Wang

2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Due to the advantages of small size, lightweight, and simple operation, the unmanned aerial vehicle (UAV) has been widely used, and it is also becoming increasingly convenient to capture high-resolution aerial images in a variety of environments. Existing target-detection methods for UAV aerial images lack outstanding performance in the face of challenges such as small targets, dense arrangement, sparse distribution, and a complex background. In response to the above problems, some improvements on the basis of YOLOv5l have been made by us. Specifically, three feature-extraction modules are proposed, using asymmetric convolutions. They are named the Asymmetric ResNet (ASResNet) module, Asymmetric Enhanced Feature Extraction (AEFE) module, and Asymmetric Res2Net (ASRes2Net) module, respectively. According to the respective characteristics of the above three modules, the residual blocks in different positions in the backbone of YOLOv5 were replaced accordingly. An Improved Efficient Channel Attention (IECA) module was added after Focus, and Group Spatial Pyramid Pooling (GSPP) was used to replace the Spatial Pyramid Pooling (SPP) module. In addition, the K-Means++ algorithm was used to obtain more accurate anchor boxes, and the new EIOU-NMS method was used to improve the postprocessing ability of the model. Finally, ablation experiments, comparative experiments, and visualization of results were performed on five datasets, namely CIFAR-10, PASCAL VOC, VEDAI, VisDrone 2019, and Forklift. The effectiveness of the improved strategies and the superiority of the proposed method (YOLO-UAV) were verified. Compared with YOLOv5l, the backbone of the proposed method increased the top-one accuracy of the classification task by 7.20% on the CIFAR-10 dataset. The mean average precision (mAP) of the proposed method on the four object-detection datasets was improved by 5.39%, 5.79%, 4.46%, and 8.90%, respectively.

show abstract

“…As artificial intelligence technology progresses and the use of unmanned aerial vehicles (UAVs) becomes more widespread in engineering applications, more and more deep learning techniques are being leveraged to solve engineering-related problems [4][5][6]. For example, many researchers have applied object detection algorithms to the task of locating manhole covers.…”

Section: Introductionmentioning

confidence: 99%

Manhole Cover Classification Based on Super-Resolution Reconstruction of Unmanned Aerial Vehicle Aerial Imagery

Wang,

Huang

2024

Applied Sciences

View full text Add to dashboard Cite

Urban underground pipeline networks are a key component of urban infrastructure, and a large number of older urban areas lack information about their underground pipelines. In addition, survey methods for underground pipelines are often time-consuming and labor-intensive. While the manhole cover serves as the hub connecting the underground pipe network with the ground, the generation of underground pipe network can be realized by obtaining the location and category information of the manhole cover. Therefore, this paper proposed a manhole cover detection method based on UAV aerial photography to obtain ground images, using image super-resolution reconstruction and image positioning and classification. Firstly, the urban image was obtained by UAV aerial photography, and then the YOLOv8 object detection technology was used to accurately locate the manhole cover. Next, the SRGAN network was used to perform super-resolution processing on the manhole cover text to improve the clarity of the recognition image. Finally, the clear manhole cover text image was input into the VGG16_BN network to realize the manhole cover classification. The experimental results showed that the manhole cover classification accuracy of this paper’s method reached 97.62%, which verified its effectiveness in manhole cover detection. The method significantly reduces the time and labor cost and provides a new method for manhole cover information acquisition.

show abstract

YOLOD: A Target Detection Method for UAV Aerial Imagery

Cited by 33 publications

References 61 publications

Improved A-Star Search Algorithm for Probabilistic Air Pollution Detection Using UAVs

Improved A-Star Search Algorithm for Probabilistic Air Pollution Detection Using UAVs

Target Detection Method of UAV Aerial Imagery Based on Improved YOLOv5

Manhole Cover Classification Based on Super-Resolution Reconstruction of Unmanned Aerial Vehicle Aerial Imagery

Contact Info

Product

Resources

About